def main():
getopts()
# Read the physics dataset
phy_data = get_data(
'/Users/nareshs/Documents/projects/base/datasets/phy_train.dat.zip',
'phy_train.dat')
# Remove all columns with only zero as the value!
idxs = []
for class_id in phy_data:
sum_arr = np.sum(phy_data[class_id], axis=0)
all_phy_data = np.array(phy_data[class_id])
for idx, val in enumerate(sum_arr):
if abs(val) == 0.0:
idxs.append(idx)
mean_arr = get_mean_arr(np.array(phy_data[class_id]))
idx = 0
for col in all_phy_data.T:
if len(np.unique(col)) == 1 or (len(np.unique(col)) == 2 and
get_col_outlier_value(idx) in col):
idxs.append(idx)
idx = idx + 1
idxs = list(set(idxs))
all_phy_data = np.delete(all_phy_data, idxs, 1)
phy_data[class_id] = all_phy_data
class_2_mean_arr = {}
for class_id in phy_data:
info('Processing data for class: ' + str(class_id))
np_nd_arr = phy_data[class_id]
mean_arr = get_mean_arr(np_nd_arr)
class_2_mean_arr[class_id] = mean_arr
# First method: Classify on the basis of distance from the mean.
# This is a very primitive classifier
phy_test_data = get_data(
'/Users/nareshs/Documents/projects/base/datasets/phy_test.dat.zip',
'phy_test.dat')
for class_id in phy_test_data:
np_nd_arr = np.array(phy_test_data[class_id])
mean_arr = get_mean_arr(np_nd_arr)
new_rows = []
for x in phy_test_data[class_id]:
n = get_processed_obs(x, mean_arr)
new_rows.append(n)
phy_test_data[class_id] = new_rows
fh = open('/tmp/test_mean_method.txt', 'w')
cnt = 50001
for x in phy_test_data:
for arr in phy_test_data[x]:
fh.write(
str(cnt) + ' ' + str(get_class(class_2_mean_arr, arr)) + '\n')
cnt = cnt + 1
fh.close()
def main():
getopts()
# Read the physics dataset
phy_data = get_data('/Users/nareshs/Documents/projects/base/datasets/phy_train.dat.zip', 'phy_train.dat')
# Remove all columns with only zero as the value!
idxs = []
for class_id in phy_data:
sum_arr = np.sum(phy_data[class_id], axis=0)
all_phy_data = np.array(phy_data[class_id])
for idx, val in enumerate(sum_arr):
if abs(val) == 0.0:
idxs.append(idx)
mean_arr = get_mean_arr(np.array(phy_data[class_id]))
idx = 0
for col in all_phy_data.T:
if len(np.unique(col)) == 1 or (len(np.unique(col)) == 2 and get_col_outlier_value(idx) in col):
idxs.append(idx)
idx = idx + 1
idxs = list(set(idxs))
all_phy_data = np.delete(all_phy_data, idxs, 1)
phy_data[class_id] = all_phy_data
class_2_mean_arr = {}
for class_id in phy_data:
info('Processing data for class: ' + str(class_id))
np_nd_arr = phy_data[class_id]
mean_arr = get_mean_arr(np_nd_arr)
class_2_mean_arr[class_id] = mean_arr
# First method: Classify on the basis of distance from the mean.
# This is a very primitive classifier
phy_test_data = get_data('/Users/nareshs/Documents/projects/base/datasets/phy_test.dat.zip', 'phy_test.dat')
for class_id in phy_test_data:
np_nd_arr = np.array(phy_test_data[class_id])
mean_arr = get_mean_arr(np_nd_arr)
new_rows = []
for x in phy_test_data[class_id]:
n = get_processed_obs(x, mean_arr)
new_rows.append(n)
phy_test_data[class_id] = new_rows
fh = open('/tmp/test_mean_method.txt', 'w')
cnt = 50001
for x in phy_test_data:
for arr in phy_test_data[x]:
fh.write(str(cnt) + ' ' + str(get_class(class_2_mean_arr, arr)) + '\n')
cnt = cnt + 1
fh.close()
def main():
getopts()
# Read the physics dataset
phy_data = get_data('/Users/nareshs/Documents/projects/base/datasets/phy_train.dat.zip', 'phy_train.dat')
# Remove all columns with only zero as the value!
idxs = []
for class_id in phy_data:
sum_arr = np.sum(phy_data[class_id], axis=0)
all_phy_data = np.array(phy_data[class_id])
for idx, val in enumerate(sum_arr):
if abs(val) == 0.0:
idxs.append(idx)
mean_arr = get_mean_arr(np.array(phy_data[class_id]))
idx = 0
for col in all_phy_data.T:
if len(np.unique(col)) == 1 or (len(np.unique(col)) == 2 and get_col_outlier_value(idx) in col):
idxs.append(idx)
idx = idx + 1
idxs = list(set(idxs))
all_phy_data = np.delete(all_phy_data, idxs, 1)
phy_data[class_id] = all_phy_data
class_2_mean_arr = {}
for class_id in phy_data:
info('Processing data for class: ' + str(class_id))
np_nd_arr = phy_data[class_id]
mean_arr = get_mean_arr(np_nd_arr)
class_2_mean_arr[class_id] = mean_arr
def main():
getopts()
# Read the physics dataset
phy_data = get_data(
'/Users/nareshs/Documents/projects/base/datasets/phy_train.dat.zip',
'phy_train.dat')
# Remove all columns with only zero as the value!
idxs = []
for class_id in phy_data:
sum_arr = np.sum(phy_data[class_id], axis=0)
all_phy_data = np.array(phy_data[class_id])
for idx, val in enumerate(sum_arr):
if abs(val) == 0.0:
idxs.append(idx)
mean_arr = get_mean_arr(np.array(phy_data[class_id]))
idx = 0
for col in all_phy_data.T:
if len(np.unique(col)) == 1 or (len(np.unique(col)) == 2 and
get_col_outlier_value(idx) in col):
idxs.append(idx)
idx = idx + 1
idxs = list(set(idxs))
all_phy_data = np.delete(all_phy_data, idxs, 1)
phy_data[class_id] = all_phy_data
class_2_mean_arr = {}
for class_id in phy_data:
info('Processing data for class: ' + str(class_id))
np_nd_arr = phy_data[class_id]
mean_arr = get_mean_arr(np_nd_arr)
class_2_mean_arr[class_id] = mean_arr
def main():
getopts()
# Read the physics dataset
phy_data = get_data('/Users/nareshs/Documents/projects/base/datasets/phy_train.dat.zip', 'phy_train.dat')
# Remove all columns with only zero as the value!
idxs = []
for class_id in phy_data:
sum_arr = np.sum(phy_data[class_id], axis=0)
all_phy_data = np.array(phy_data[class_id])
for idx, val in enumerate(sum_arr):
if abs(val) == 0.0:
idxs.append(idx)
mean_arr = get_mean_arr(np.array(phy_data[class_id]))
idx = 0
for col in all_phy_data.T:
if len(np.unique(col)) == 1 or (len(np.unique(col)) == 2 and get_col_outlier_value(idx) in col):
idxs.append(idx)
idx = idx + 1
idxs = list(set(idxs))
all_phy_data = np.delete(all_phy_data, idxs, 1)
phy_data[class_id] = all_phy_data
class_2_mean_arr = {}
for class_id in phy_data:
info('Processing data for class: ' + str(class_id))
np_nd_arr = phy_data[class_id]
mean_arr = get_mean_arr(np_nd_arr)
class_2_mean_arr[class_id] = mean_arr
# Second method: Linear regression
# Simply put, we will be calculating [b1, b2, b3 .. bn] such that
# for the ith observation:
# yi = b1 * x1i + b2 * x2i ... + bn * xni
# where n is the number of distinct attributes
# More details at: http://en.wikipedia.org/wiki/Regression_analysis
# Derivation at: http://en.wikipedia.org/wiki/Linear_least_squares_(mathematics)
# y contains the class_ids corresponding to each observation
y = []
# x contains all the observations
x = []
for class_id in phy_data:
for obs in phy_data[class_id]:
y.append(int(class_id))
processed_obs = get_processed_obs(obs, class_2_mean_arr[class_id])
x.append(processed_obs)
x = np.array(x)
y = np.array(y)
info('Created x and y np arrays')
x_t = x.T
info('Calculated x.T')
xt_dot_y = x_t.dot(y)
info('Calculated x_t.dot(y)')
# we want to calculate (x_t * x)-1 * xt_dot_y
x_t_x = x_t.dot(x)
info('Calculated x_t_x')
x_t_x_i = np.linalg.inv(x_t_x)
info('Calculated inv(x_t_x)')
b = x_t_x_i.dot(xt_dot_y)
fh = open('/tmp/test_linalg.txt', 'w')
cnt = 50001
for x in phy_test_data:
for arr in phy_test_data[x]:
l = len(arr)
arr = np.delete(np.array(arr).reshape(1, l), idxs, 1)
val = np.sum(b * arr)
fh.write(str(cnt) + ' ' + str(val) + '\n')
cnt = cnt + 1
fh.close()
def main():
getopts()
# Read the physics dataset
phy_data = get_data(
'/Users/nareshs/Documents/projects/base/datasets/phy_train.dat.zip',
'phy_train.dat')
# Remove all columns with only zero as the value!
idxs = []
for class_id in phy_data:
sum_arr = np.sum(phy_data[class_id], axis=0)
all_phy_data = np.array(phy_data[class_id])
for idx, val in enumerate(sum_arr):
if abs(val) == 0.0:
idxs.append(idx)
mean_arr = get_mean_arr(np.array(phy_data[class_id]))
idx = 0
for col in all_phy_data.T:
if len(np.unique(col)) == 1 or (len(np.unique(col)) == 2 and
get_col_outlier_value(idx) in col):
idxs.append(idx)
idx = idx + 1
idxs = list(set(idxs))
all_phy_data = np.delete(all_phy_data, idxs, 1)
phy_data[class_id] = all_phy_data
class_2_mean_arr = {}
for class_id in phy_data:
info('Processing data for class: ' + str(class_id))
np_nd_arr = phy_data[class_id]
mean_arr = get_mean_arr(np_nd_arr)
class_2_mean_arr[class_id] = mean_arr
# Second method: Linear regression
# Simply put, we will be calculating [b1, b2, b3 .. bn] such that
# for the ith observation:
# yi = b1 * x1i + b2 * x2i ... + bn * xni
# where n is the number of distinct attributes
# More details at: http://en.wikipedia.org/wiki/Regression_analysis
# Derivation at: http://en.wikipedia.org/wiki/Linear_least_squares_(mathematics)
# y contains the class_ids corresponding to each observation
y = []
# x contains all the observations
x = []
for class_id in phy_data:
for obs in phy_data[class_id]:
y.append(int(class_id))
processed_obs = get_processed_obs(obs, class_2_mean_arr[class_id])
x.append(processed_obs)
x = np.array(x)
y = np.array(y)
info('Created x and y np arrays')
x_t = x.T
info('Calculated x.T')
xt_dot_y = x_t.dot(y)
info('Calculated x_t.dot(y)')
# we want to calculate (x_t * x)-1 * xt_dot_y
x_t_x = x_t.dot(x)
info('Calculated x_t_x')
x_t_x_i = np.linalg.inv(x_t_x)
info('Calculated inv(x_t_x)')
b = x_t_x_i.dot(xt_dot_y)
fh = open('/tmp/test_linalg.txt', 'w')
cnt = 50001
for x in phy_test_data:
for arr in phy_test_data[x]:
l = len(arr)
arr = np.delete(np.array(arr).reshape(1, l), idxs, 1)
val = np.sum(b * arr)
fh.write(str(cnt) + ' ' + str(val) + '\n')
cnt = cnt + 1
fh.close()
def main():
getopts()
# Read the physics dataset
phy_data = get_data(
'/Users/nareshs/Documents/projects/base/datasets/phy_train.dat.zip',
'phy_train.dat')
# Remove all columns with only zero as the value!
idxs = []
for class_id in phy_data:
sum_arr = np.sum(phy_data[class_id], axis=0)
all_phy_data = np.array(phy_data[class_id])
for idx, val in enumerate(sum_arr):
if abs(val) == 0.0:
idxs.append(idx)
mean_arr = get_mean_arr(np.array(phy_data[class_id]))
idx = 0
for col in all_phy_data.T:
if len(np.unique(col)) == 1 or (len(np.unique(col)) == 2 and
get_col_outlier_value(idx) in col):
idxs.append(idx)
idx = idx + 1
idxs = list(set(idxs))
all_phy_data = np.delete(all_phy_data, idxs, 1)
phy_data[class_id] = all_phy_data
class_2_mean_arr = {}
for class_id in phy_data:
info('Processing data for class: ' + str(class_id))
np_nd_arr = phy_data[class_id]
mean_arr = get_mean_arr(np_nd_arr)
class_2_mean_arr[class_id] = mean_arr
# Third method: Perceptron learning algorithm
# http://en.wikipedia.org/wiki/Perceptron#Learning_algorithm
# http://page.mi.fu-berlin.de/rojas/neural/chapter/K4.pdf
# More detailed: http://hagan.okstate.edu/4_Perceptron.pdf
# Initialize the weights array
w0 = [0.0] * (phy_data['1'][0].shape[0] + 1)
w = [w0]
info('Initialized weights array of length ' +
str(phy_data['1'][0].shape[0]))
# Initialize threshold
gamma = 0.01
# Initialize learning rate
alpha = 0.1
all_data = []
for class_id in phy_data:
for row in phy_data[class_id]:
row = [1.0] + list(row)
all_data.append((class_id, np.array(row)))
iter_num = 1
print 'Entering the while loop'
latest_sum_of_errors = float('inf')
while True:
print datetime.now(), ': Iterating over all data. No.:', iter_num
for row_num, row in enumerate(all_data):
expected_val = float(row[0])
f_val = sum(w[-1] * row[1])
f_val = 1 if f_val > 0 else 0
#print datetime.now(), ': Getting new weights'
w_new = []
for idx, x in enumerate(w[-1]):
w_new.append(x + alpha * (expected_val - f_val) * row[1][idx])
#print datetime.now(), ': Got new weights'
w.append(w_new)
print datetime.now(), 'Done getting weights. Now checking the error'
# Check the error!
total_num_obs = len(all_data)
sum_of_errors = 0.0
for test_row in all_data:
expected_val = float(test_row[0])
f_val = sum(test_row[1] * w_new)
f_val = 1 if f_val > 0 else 0
sum_of_errors += abs(expected_val - f_val)
print datetime.now(
), ': Got sum of errors: ', sum_of_errors, ' for ', total_num_obs, ' data points'
avg_error = sum_of_errors / total_num_obs
if avg_error < gamma:
break
print 'After processing ', row_num, ' got avg_error', avg_error
# Increase the iteration count
iter_num = iter_num + 1
cnt = 50001
for x in phy_test_data:
for arr in phy_test_data[x]:
l = len(arr)
arr = np.delete(np.array(arr).reshape(1, l), idxs, 1)
val = np.sum(w[-1] * arr)
print cnt, val
cnt = cnt + 1
def main():
getopts()
# Read the physics dataset
phy_data = get_data('/Users/nareshs/Documents/projects/base/datasets/phy_train.dat.zip', 'phy_train.dat')
# Remove all columns with only zero as the value!
idxs = []
for class_id in phy_data:
sum_arr = np.sum(phy_data[class_id], axis=0)
all_phy_data = np.array(phy_data[class_id])
for idx, val in enumerate(sum_arr):
if abs(val) == 0.0:
idxs.append(idx)
mean_arr = get_mean_arr(np.array(phy_data[class_id]))
idx = 0
for col in all_phy_data.T:
if len(np.unique(col)) == 1 or (len(np.unique(col)) == 2 and get_col_outlier_value(idx) in col):
idxs.append(idx)
idx = idx + 1
idxs = list(set(idxs))
all_phy_data = np.delete(all_phy_data, idxs, 1)
phy_data[class_id] = all_phy_data
class_2_mean_arr = {}
for class_id in phy_data:
info('Processing data for class: ' + str(class_id))
np_nd_arr = phy_data[class_id]
mean_arr = get_mean_arr(np_nd_arr)
class_2_mean_arr[class_id] = mean_arr
# Third method: Perceptron learning algorithm
# http://en.wikipedia.org/wiki/Perceptron#Learning_algorithm
# http://page.mi.fu-berlin.de/rojas/neural/chapter/K4.pdf
# More detailed: http://hagan.okstate.edu/4_Perceptron.pdf
# Initialize the weights array
w0 = [0.0] * (phy_data['1'][0].shape[0] + 1)
w = [w0]
info('Initialized weights array of length ' + str(phy_data['1'][0].shape[0]))
# Initialize threshold
gamma = 0.01
# Initialize learning rate
alpha = 0.1
all_data = []
for class_id in phy_data:
for row in phy_data[class_id]:
row = [1.0] + list(row)
all_data.append((class_id, np.array(row)))
iter_num = 1
print 'Entering the while loop'
latest_sum_of_errors = float('inf')
while True:
print datetime.now(), ': Iterating over all data. No.:', iter_num
for row_num, row in enumerate(all_data):
expected_val = float(row[0])
f_val = sum(w[-1] * row[1])
f_val = 1 if f_val > 0 else 0
#print datetime.now(), ': Getting new weights'
w_new = []
for idx, x in enumerate(w[-1]):
w_new.append(x + alpha * (expected_val - f_val) * row[1][idx])
#print datetime.now(), ': Got new weights'
w.append(w_new)
print datetime.now(), 'Done getting weights. Now checking the error'
# Check the error!
total_num_obs = len(all_data)
sum_of_errors = 0.0
for test_row in all_data:
expected_val = float(test_row[0])
f_val = sum(test_row[1] * w_new)
f_val = 1 if f_val > 0 else 0
sum_of_errors += abs(expected_val - f_val)
print datetime.now(), ': Got sum of errors: ', sum_of_errors, ' for ', total_num_obs, ' data points'
avg_error = sum_of_errors / total_num_obs
if avg_error < gamma:
break
print 'After processing ', row_num, ' got avg_error', avg_error
# Increase the iteration count
iter_num = iter_num + 1
cnt = 50001
for x in phy_test_data:
for arr in phy_test_data[x]:
l = len(arr)
arr = np.delete(np.array(arr).reshape(1, l), idxs, 1)
val = np.sum(w[-1] * arr)
print cnt, val
cnt = cnt + 1